Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 13180
    Prev
    Next
    INDEX
    Explanations

    technical terms and measurements related to image processing and transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.47
    
    -0.47
     numberWith
    -0.43
    richTextPanel
    -0.40
     CreateTagHelper
    -0.37
    Autoritní
    -0.36
     useCallback
    -0.33
    
    -0.32
    shadowOpacity
    -0.31
    
    -0.31
    POSITIVE LOGITS
     shift
    2.27
     shifted
    2.06
    shift
    2.02
     shifts
    2.02
     Shift
    1.98
     shifting
    1.95
    Shift
    1.93
     offset
    1.92
     SHIFT
    1.83
    shifted
    1.77
    Activations Density 1.474%

    No Known Activations